ScanObjectNN

doi:doi:10.57702/ohxx4y9s

ScanObjectNN

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes.

BibTex:

@dataset{Mikaela_Angelina_Uy_and_Quang-Hieu_Pham_and_Binh-Son_Hua_and_Duc_Thanh_Nguyen_and_Sai-Kit_Yeung_2024,
    abstract = {Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes.},
    author = {Mikaela Angelina Uy and Quang-Hieu Pham and Binh-Son Hua and Duc Thanh Nguyen and Sai-Kit Yeung},
    doi = {10.57702/ohxx4y9s},
    institution = {No Organization},
    keyword = {'3D Models', '3D Object Recognition', '3D Objects', '3D Scans', '3D computer vision', '3D models', '3D object', '3D object recognition', '3D objects', '3D point cloud', '3D point clouds', 'CAD models', 'Few-shot Learning', 'Object Classification', 'Object Recognition', 'Object recognition', 'Part Segmentation', 'Point Clouds', 'ScanObjectNN', 'Shape Recognition', 'category annotations', 'classification', 'object recognition', 'point cloud', 'point cloud completion', 'point cloud data', 'real-world data', 'scene understanding'},
    month = {nov},
    publisher = {TIB},
    title = {ScanObjectNN},
    url = {https://service.tib.eu/ldmservice/dataset/scanobjectnn},
    year = {2024}
}